AI Hardware
Apple Neural Engine: Programming for Real Performance
I spent three months in 2025 trying to get a production recommendation model to run efficiently on Apple Silicon. The GPU path worked fine. The CPU path was ...
Who Has the Largest GPU Cluster? (2026 Guide)
We get this question at SIVARO at least twice a week. A founder calls, says they’re building the next frontier model, and asks: "Who has the largest GPU cl...
What Are the 4 Types of Computer Architecture? A Practitioner's Guide for AI & Data Infrastructure
If you're building production AI systems, you need to know what are the 4 types of computer architecture — not because some textbook says so, but because p...
How to Make Your Own GPU Cluster
I ran my first real training job on a homemade GPU cluster in 2019. Four RTX 2080 Ti's duct-taped to a mining frame, connected with a cheap switch, and power...
Always-On AI Glasses: A Practitioner’s Guide to Building the Invisible Interface
I spent six months in 2025 telling founders their “AI glasses” idea was a hardware problem. Then I built one. Turns out I was wrong. The problem isn’t ...
Is LLM Inference Profitable? A Practitioner's Guide to the Economics of AI Serving
Last year, a CTO I know spent $80,000 on GPU clusters to serve a custom chatbot. Three months later, the project was dead. Not because the model was bad. But...
South Korea Memory Chip Production Humanoid Robots: The Factory Floor Revolution
You're reading this because you saw the headline and thought "finally, someone who's actually built something in this space." I'm Nishaant Dixit. I run SIVAR...